Implementation notes: amd64, h3neo, crypto_core/wforcesntrup1013

Computer: h3neo
Microarchitecture: amd64; K10 45nm (100f63)
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20240107
Operation: crypto_core
Primitive: wforcesntrup1013

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
609	2356 0 0	19939 844 928	`ref2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
610	2233 0 0	18139 844 928	`ref2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
700	1577 0 0	15027 844 928	`ref2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
726	1906 0 0	17819 844 928	`simpler`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
748	2011 0 0	19587 844 928	`simpler`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
781	1218 0 0	14675 844 928	`simpler`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
851	604 0 0	15685 804 992	`simpler`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
959	604 0 0	15685 804 992	`ref2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
1209	2677 0 0	19907 844 928	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
1212	2528 0 0	18075 844 928	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
1238	1808 0 0	14899 844 928	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
1486	1120 0 0	16285 804 992	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
2962	225 0 0	12707 844 928	`ref2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
2969	210 0 0	12029 836 928	`ref2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
3537	235 0 0	12739 844 928	`simpler`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
3543	222 0 0	12061 836 928	`simpler`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
3687	273 0 0	11992 780 960	`ref2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
3693	295 0 0	13292 796 992	`ref2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
3995	272 0 0	11992 780 960	`simpler`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
4569	192 0 0	12299 844 928	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
4723	232 0 0	13973 804 992	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
4858	293 0 0	13260 796 992	`simpler`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
5128	162 0 0	11621 836 928	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231216	20231212
5949	293 0 0	13965 804 992	`ref2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
6432	201 0 0	13252 796 992	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
7558	293 0 0	13965 804 992	`simpler`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212
7840	191 0 0	11960 780 960	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231216	20231212

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

wforce.c: wforce.c:24:13: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_wforcesntrup1013_avx_constbranchindex' that is compiled without support for 'avx'
wforce.c: maskvec = _mm256_set1_epi16(~mask);
wforce.c: ^
wforce.c: wforce.c:24:13: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
wforce.c: wforce.c:29:19: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_wforcesntrup1013_avx_constbranchindex' that is compiled without support for 'avx'
wforce.c: __m256i x = _mm256_loadu_si256((__m256i *) in);
wforce.c: ^
wforce.c: wforce.c:29:19: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
wforce.c: wforce.c:30:12: error: always_inline function '_mm256_set1_epi8' requires target feature 'avx', but would be inlined into function 'crypto_core_wforcesntrup1013_avx_constbranchindex' that is compiled without support for 'avx'
wforce.c: x ^= _mm256_set1_epi8(1);
wforce.c: ^
wforce.c: wforce.c:30:12: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
wforce.c: wforce.c:32:12: error: always_inline function '_mm256_set1_epi8' requires target feature 'avx', but would be inlined into function 'crypto_core_wforcesntrup1013_avx_constbranchindex' that is compiled without support for 'avx'
wforce.c: x ^= _mm256_set1_epi8(1);
wforce.c: ^
wforce.c: wforce.c:32:12: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
wforce.c: wforce.c:33:7: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_wforcesntrup1013_avx_constbranchindex' that is compiled without support for 'avx'
wforce.c: _mm256_storeu_si256((__m256i *) out,x);
wforce.c: ^
wforce.c: wforce.c:33:7: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
wforce.c: wforce.c:46:19: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_wforcesntrup1013_avx_constbranchindex' that is compiled without support for 'avx'
wforce.c: __m256i x = _mm256_loadu_si256((__m256i *) in);
wforce.c: ^
wforce.c: wforce.c:46:19: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
wforce.c: wforce.c:48:7: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_wforcesntrup1013_avx_constbranchindex' that is compiled without support for 'avx'
wforce.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

wforce.c: wforce.c: In function 'crypto_core_wforcesntrup1013_avx_constbranchindex':
wforce.c: wforce.c:24:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
wforce.c: 24 | maskvec = _mm256_set1_epi16(~mask);
wforce.c: | ~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
wforce.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:43,
wforce.c: from wforce.c:1:
wforce.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h:1333:1: error: inlining failed in call to 'always_inline' '_mm256_set1_epi16': target specific option mismatch
wforce.c: 1333 | _mm256_set1_epi16 (short __A)
wforce.c: | ^~~~~~~~~~~~~~~~~
wforce.c: wforce.c:24:13: note: called from here
wforce.c: 24 | maskvec = _mm256_set1_epi16(~mask);
wforce.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
wforce.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:43,
wforce.c: from wforce.c:1:
wforce.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h:933:1: error: inlining failed in call to 'always_inline' '_mm256_storeu_si256': target specific option mismatch
wforce.c: 933 | _mm256_storeu_si256 (__m256i_u *__P, __m256i __A)
wforce.c: | ^~~~~~~~~~~~~~~~~~~
wforce.c: wforce.c:33:7: note: called from here
wforce.c: 33 | _mm256_storeu_si256((__m256i *) out,x);
wforce.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
wforce.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:43,
wforce.c: from wforce.c:1:
wforce.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h:1340:1: error: inlining failed in call to 'always_inline' '_mm256_set1_epi8': target specific option mismatch
wforce.c: 1340 | _mm256_set1_epi8 (char __A)
wforce.c: | ^~~~~~~~~~~~~~~~
wforce.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx